What's New? Summarizing Contributions in Scientific Literature

TL;DR

This paper introduces a new task of disentangled paper summarization to separately highlight contributions and context, enhancing the clarity of scientific article summaries, supported by dataset extensions, baseline models, and evaluation protocols.

Contribution

It presents the first framework for disentangled summarization of scientific papers, extending the S2ORC corpus with new labels and analyzing multiple baseline models.

Findings

Disentangled summaries are considered more helpful in 79% of cases by experts.

Proposed models effectively generate separate contribution and context summaries.

New evaluation protocol measures relevance, novelty, and disentanglement.

Abstract

With thousands of academic articles shared on a daily basis, it has become increasingly difficult to keep up with the latest scientific findings. To overcome this problem, we introduce a new task of disentangled paper summarization, which seeks to generate separate summaries for the paper contributions and the context of the work, making it easier to identify the key findings shared in articles. For this purpose, we extend the S2ORC corpus of academic articles, which spans a diverse set of domains ranging from economics to psychology, by adding disentangled "contribution" and "context" reference labels. Together with the dataset, we introduce and analyze three baseline approaches: 1) a unified model controlled by input code prefixes, 2) a model with separate generation heads specialized in generating the disentangled outputs, and 3) a training strategy that guides the model using additional supervision coming from inbound and outbound citations. We also propose a comprehensive automatic evaluation protocol which reports the relevance, novelty, and disentanglement of generated outputs. Through a human study involving expert annotators, we show that in 79%, of cases our new task is considered more helpful than traditional scientific paper summarization.